Triple
T37469550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leftoverture |
E931118
|
entity |
| Predicate | yearEndChartUSBillboard2001977 |
P118955
|
FINISHED |
| Object | 32 |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 32 | Statement: [Leftoverture, yearEndChartUSBillboard2001977, 32]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearEndChartUSBillboard2001977 Context triple: [Leftoverture, yearEndChartUSBillboard2001977, 32]
-
A.
yearEndChartUSBillboardHot100
Indicates that the subject achieved a position on the U.S. Billboard Hot 100 year-end chart in the specified year.
-
B.
chartPositionUSBillboardYearEnd
chosen
Indicates the position an item holds on the U.S. Billboard year-end chart for a given year.
-
C.
enteredBillboardHot100Top10Year
Indicates that an entity (typically a song or artist) reached the top 10 positions of the Billboard Hot 100 chart in a specified year.
-
D.
chartPositionUSBillboard200
Indicates the position an album or release achieved on the US Billboard 200 chart.
-
E.
chartPositionUSBillboardHot100Peak
Indicates the highest ranking an item has ever reached on the US Billboard Hot 100 chart.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76ec2af148190897d101070d7f415 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8e3c8e248190b4a4067b9262c845 |
completed | May 6, 2026, 6:53 p.m. |
| PD | Predicate disambiguation | batch_69fb8d0c53c08190b64291bac58cdb4c |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:17 p.m.